Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

Model Description by Creator

CLIP (ViT-L/14) is a text encoder that all of these stable diffusion models were trained on. All of SD 1.0 through 1.5 were trained on a fixed CLIP. LoRAs, Finetunes, and merges on the other hand modify CLIP to add new concepts. The result? In our model universe, our CLIP has been pretty abused and often strayed too far from the original. I initially merged a lot of CLIPs I thought worked well for certain things, but now I realize that we have to start feeding v1.5's CLIP back in to move forward.

v1.7 partially merges in bits from three of my experimental models:

heater, a custom model sampled from 47 anime models; dare-ties at 8%.

fullpoint, a custom model sampled from 37 other general models I had fp32 data for; dare-ties at 8%..

darkness, a custom model sampled from 57 artistic models; block merged in [30%, .20%, 10%].

Really just a taste of each. Since all of these models are so strongly pooled, adding each one in mixed in some really strong core structure. If you look at the workflows in the images, you can see the CFG is pretty high, as are the number of steps (50 seemed good for 768x1152), using dpmpp 2/3m sde and CFG of 10+ in parts. I even got decent images using exponential sampling in some cases. Artifacts on faces are very rare, and hands generally work pretty well.

I also 50/50 merged my cybernetic dreams CLIP, cleaning up a lot of strange issues.

That structure I added should make this version much more stable when using both LoRAs and LCM as well.

v1.6 attempted to improve hands and other details. It uses the new DARE-TIES merge to cherry pick these while maintaining some of the stylistic qualities; along with some creative use of the skin-hands LORA (https://huggingface.co/imagepipeline/Skin-and-Hands), which is very good. I've been using https://civitai.com/models/116230?modelVersionId=125849 bad hands 5 to clean up most of the remaining glitches.

v1.5 applies https://huggingface.co/bdsqlsz/dpo-sd-text2image-v1-fp16 DPO model to provide some more structure.

This model's lineage is originally DarkSun, as I liked it's style, but it may have some very different powers as it has been subjected to a lot of theories that I have about how diffusion models work (and a lot of merging)... v1.4 was an experiment using FreeU as a model preprocessor, but upon further testing, it doesn't seem to have an impact on the final results. Why? FreeU is an outblock preprocessor.

For any users, post your best images (with prompts) and I will use them for DPO in the future.

Hearts/5-stars if you want me to continue working on this one.

Try different clip skips, can handle very high CFG (9+) and really aggressive sampling.

Disclaimer:
This model is not intended to produce CSAM. Do not use it for this purpose.

Images Generated With This Model

cinematic photo (art by Mathias Goeritz:0.9) , photograph, Lush Girlfriend, Tax collector, Rich ginger hair, Winter, tilt shift, Horror, specular lighting, film grain,(cinematic still:1.2), (freckles), professional, 4k, highly detailed
N/A
Hidden For Public Users
cinematic photo (art by Mathias Goeritz:0.9) , photograph, Lush Girlfriend, Tax collector, Rich ginger hair, Winter, tilt shift, Horror, specular lighting, film grain,(cinematic still:1.2), (freckles), professional, 4k, highly detailed
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
beautiful scenery nature glass bottle landscape, , purple galaxy bottle,
N/A
Hidden For Public Users
beautiful scenery nature glass bottle landscape, , purple galaxy bottle,
beautiful scenery nature glass bottle landscape, , purple galaxy bottle,
N/A
Hidden For Public Users
beautiful scenery nature glass bottle landscape, , purple galaxy bottle,
a woman holding a teapot, shopping, looking at viewer
N/A
Hidden For Public Users
a woman holding a teapot, shopping, looking at viewer
cinematic photo (art by Mathias Goeritz:0.9) , photograph, Lush Girlfriend, Tax collector, Rich ginger hair, Winter, tilt shift, Horror, specular lighting, film grain,(cinematic still:1.2), (freckles), professional, 4k, highly detailed
N/A
Hidden For Public Users
cinematic photo (art by Mathias Goeritz:0.9) , photograph, Lush Girlfriend, Tax collector, Rich ginger hair, Winter, tilt shift, Horror, specular lighting, film grain,(cinematic still:1.2), (freckles), professional, 4k, highly detailed
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
1girl, fullbody, standing, slim, (bamboo trees), kabuto, red samurai armor, misty air, strong sunlight, mossy path, mountain village, huge weapon, mountain top scenery, full length robes, pants, shoes
N/A
Hidden For Public Users
1girl, fullbody, standing, slim, (bamboo trees), kabuto, red samurai armor, misty air, strong sunlight, mossy path, mountain village, huge weapon, mountain top scenery, full length robes, pants, shoes
(centered, upper body, 1girl, woman, smirk, long wavy white hair, (pink eyes:1.2), torn cutoff shirt, looking at viewer:1.1), (wide shot:1.4), plains, bushes, forest, river, flowing river, volumetric lighting, godray, fish, birds, bonfire on top of building, masterpiece:1.2, photorealistic:1.2, girl focus, volumetric lighting, embedding:sd15/pos/edgquality:1.2
N/A
Hidden For Public Users
(centered, upper body, 1girl, woman, smirk, long wavy white hair, (pink eyes:1.2), torn cutoff shirt, looking at viewer:1.1), (wide shot:1.4), plains, bushes, forest, river, flowing river, volumetric lighting, godray, fish, birds, bonfire on top of building, masterpiece:1.2, photorealistic:1.2, girl focus, volumetric lighting, embedding:sd15/pos/edgquality:1.2
(high contrast, 2D, stylized art, watercolor (medium)), (painterly:1.2), 1girl, fire, blue eyes, black and red hair, portrait, (molten rock:1.1), volcano, smile, sky, breasts, cleavage, embedding:sd15/style/fcPortrait, 
full body shot, (red riding hood), kneeling, embedding:sd15/pos/edgquality:1.2,
N/A
Hidden For Public Users
(high contrast, 2D, stylized art, watercolor (medium)), (painterly:1.2), 1girl, fire, blue eyes, black and red hair, portrait, (molten rock:1.1), volcano, smile, sky, breasts, cleavage, embedding:sd15/style/fcPortrait, full body shot, (red riding hood), kneeling, embedding:sd15/pos/edgquality:1.2,
(high contrast, 2D, stylized art, watercolor (medium)), (painterly:1.2), 1girl, fire, blue eyes, black and red hair, portrait, (molten rock:1.1), volcano, smile, sky, breasts, cleavage, embedding:sd15/style/fcPortrait, 
full body shot, (red riding hood), kneeling, embedding:sd15/pos/edgquality:1.2,
N/A
Hidden For Public Users
(high contrast, 2D, stylized art, watercolor (medium)), (painterly:1.2), 1girl, fire, blue eyes, black and red hair, portrait, (molten rock:1.1), volcano, smile, sky, breasts, cleavage, embedding:sd15/style/fcPortrait, full body shot, (red riding hood), kneeling, embedding:sd15/pos/edgquality:1.2,
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
(monochrome:1.3), (Comic art), (medium shot), of a sexy woman, running, (holding weapon, holding), (aiming), (future sci-fi ray gun), (in a space station corridor), flat colors, black line art, low camera angle, innerboob, dynamic pose,  serious, looking confident, looking serious, looking off into distance, pointy ears, ponytail, huge breasts, black sclera, black eyes, (platinum white hair:1.1),
N/A
Hidden For Public Users
(monochrome:1.3), (Comic art), (medium shot), of a sexy woman, running, (holding weapon, holding), (aiming), (future sci-fi ray gun), (in a space station corridor), flat colors, black line art, low camera angle, innerboob, dynamic pose, serious, looking confident, looking serious, looking off into distance, pointy ears, ponytail, huge breasts, black sclera, black eyes, (platinum white hair:1.1),
1girl, fullbody, standing, slim, (bamboo trees), kabuto, red samurai armor, misty air, strong sunlight, mossy path, mountain village, huge weapon, mountain top scenery, full length robes, pants, shoes
N/A
Hidden For Public Users
1girl, fullbody, standing, slim, (bamboo trees), kabuto, red samurai armor, misty air, strong sunlight, mossy path, mountain village, huge weapon, mountain top scenery, full length robes, pants, shoes
(high contrast, 2D, stylized art, watercolor (medium)), (painterly:1.2), 1girl, fire, blue eyes, black and red hair, portrait, (molten rock:1.1), volcano, smile, sky, breasts, cleavage, embedding:sd15/style/fcPortrait, 
full body shot, (red riding hood), kneeling, embedding:sd15/pos/edgquality:1.2,
N/A
Hidden For Public Users
(high contrast, 2D, stylized art, watercolor (medium)), (painterly:1.2), 1girl, fire, blue eyes, black and red hair, portrait, (molten rock:1.1), volcano, smile, sky, breasts, cleavage, embedding:sd15/style/fcPortrait, full body shot, (red riding hood), kneeling, embedding:sd15/pos/edgquality:1.2,
Loading Free Tools...

Similar Models

AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.